AMD Radeon 660M vs NVIDIA GeForce GTX 1660 Comparison

Head-to-Head Benchmarks

The benchmark data delivers a clear verdict: the NVIDIA GeForce GTX 1660 dominates the AMD Radeon 660M in every recorded test. The database includes two head-to-head comparisons, both Geekbench workloads, and the GTX 1660 wins both by a wide margin.

In Geekbench OpenCL, the GTX 1660 scores 47,850 against the Radeon 660M's 12,876. That is a delta of -73.1% for the AMD part, meaning the NVIDIA card delivers roughly 3.7 times the raw compute performance in this workload. The gap is slightly narrower in Geekbench Vulkan, where the GTX 1660 posts 50,137 versus 14,748 for the Radeon 660M, a -70.6% delta. Even in the more favorable API for the AMD architecture, the NVIDIA part still more than triples the integrated GPU's output.

Looking at the broader database context, the Radeon 660M's average benchmark score is 13,812, which places it at the 55th percentile of all GPUs. The GTX 1660's average score is 11,680, sitting at the 51st percentile. This is a curious inversion: the GTX 1660 wins the head-to-head tests decisively, yet its overall average score is lower than the Radeon 660M's average. The explanation lies in the test mix. The Radeon 660M has only two recorded benchmarks, both Geekbench workloads where it scores relatively close to its average. The GTX 1660 has ten recorded benchmarks, including several Passmark tests (DirectX 9, 10, 11, 12, G2D, G3D, and GPU compute) that drag its average down. For instance, the GTX 1660 scores only 49 in Passmark DirectX 12 and 61 in Passmark DirectX 10, numbers that are not comparable to Geekbench scores but still pull the arithmetic mean lower.

The nearest rival data further contextualizes both parts. The Radeon 660M's closest competitors are the NVIDIA RTX A2000 Mobile (13,821 average, -0.1% delta), the AMD Radeon RX 570X (13,871, -0.4%), the AMD Radeon RX 7900 XT (13,745, +0.5%), and the NVIDIA Tesla K10 (14,029, -1.5%). Every one of these rivals sits within 1.5% of the Radeon 660M's average, indicating that the integrated GPU performs in a tight cluster around the 13,800 mark. The GTX 1660's nearest rivals include the AMD Radeon RX 7800 XT (11,627, +0.5%), the AMD Radeon Pro 5500M (11,528, +1.3%), the AMD Radeon RX 6500 XT (11,842, -1.4%), and the NVIDIA Tesla K20c (11,479, +1.8%). The GTX 1660's average is also tightly clustered, within 1.8% of all four rivals, but the cluster sits roughly 2,000 points lower than the Radeon 660M's cluster.

For users focused solely on the two Geekbench tests, the GTX 1660 is the unequivocal winner. The data shows no test where the Radeon 660M takes a victory. The winsA count is zero; the winsB count is two.

FAQ

Q: Which GPU wins in Geekbench OpenCL performance?

A: The NVIDIA GeForce GTX 1660 wins decisively, scoring 47,850 against the AMD Radeon 660M's 12,876, a delta of -73.1% for the AMD part.

Q: Is the Radeon 660M competitive in Vulkan workloads?

A: No. The GTX 1660 scores 50,137 in Geekbench Vulkan compared to 14,748 for the Radeon 660M, a -70.6% delta. The AMD integrated GPU trails by more than a factor of three.

Q: Why does the Radeon 660M have a higher average benchmark score than the GTX 1660 if it loses every head-to-head test?

A: The Radeon 660M has only two recorded benchmarks, both Geekbench tests where it scores near its 13,812 average. The GTX 1660 has ten recorded benchmarks, including several Passmark tests with low scores (49 in DirectX 12, 61 in DirectX 10, 79 in DirectX 11, 177 in DirectX 9) that lower its overall average to 11,680 despite its strong Geekbench results.

Q: How does the Radeon 660M compare to its nearest rivals in the database?

A: The Radeon 660M's average score of 13,812 places it within 1.5% of all four nearest rivals: the RTX A2000 Mobile (-0.1%), RX 570X (-0.4%), RX 7900 XT (+0.5%), and Tesla K10 (-1.5%). It is effectively a mid-pack performer in its own cluster.

Q: What is the GTX 1660's standing among its nearest rivals?

A: The GTX 1660's average of 11,680 is within 1.8% of all four nearest rivals: the RX 7800 XT (+0.5%), Radeon Pro 5500M (+1.3%), RX 6500 XT (-1.4%), and Tesla K20c (+1.8%). Its cluster sits about 2,000 points below the Radeon 660M's cluster.

Q: Does the Radeon 660M have any recorded benchmark win over the GTX 1660?

A: No. The database records zero wins for the Radeon 660M and two wins for the GTX 1660 across the two head-to-head tests.

Architecture Differences

The two GPUs come from fundamentally different design philosophies. The AMD Radeon 660M is built on the RDNA 2.0 architecture using TSMC's 6 nm process node, with a chip codenamed Rembrandt. It belongs to the Navi II IGP generation, specifically for Rembrandt Mobile, and is an integrated graphics processor. The NVIDIA GeForce GTX 1660 uses the Turing architecture on a 12 nm TSMC process, with the TU116 chip, and belongs to the GeForce 16 series.

The transistor counts diverge sharply. The Radeon 660M packs 13,100 million transistors on a 208 mm² die, yielding a transistor density of 63.0 million per mm². The GTX 1660 contains 6,600 million transistors on a larger 284 mm² die, with a density of only 23.2 million per mm². The AMD part achieves roughly 2.7 times the transistor density thanks to the more advanced 6 nm node, but the NVIDIA chip uses a larger die overall.

The Radeon 660M includes 6 ray tracing cores, a feature entirely absent from the GTX 1660, which lists no RT cores and no tensor cores. Neither GPU has tensor cores. The Radeon 660M supports DirectX 12 Ultimate (12_2), while the GTX 1660 is limited to DirectX 12 (12_1). Both support OpenGL 4.6 and Vulkan 1.4, so API compatibility is otherwise identical.

The memory architecture could not be more different. The Radeon 660M uses system shared memory, with the size, type, bus width, and bandwidth all listed as "System Shared" or "System Dependent." The GTX 1660 has dedicated 6 GB of GDDR5 memory on a 192-bit bus, delivering 192.1 GB/s of bandwidth. This dedicated memory arrangement is a major factor in the GTX 1660's performance advantage in the recorded benchmarks.

The bus interface also differs: the Radeon 660M uses PCIe 4.0 x8, while the GTX 1660 uses PCIe 3.0 x16. Display outputs on the AMD part are "Portable Device Dependent," reflecting its IGP nature, whereas the GTX 1660 provides 1x DVI, 1x HDMI 2.0, and 1x DisplayPort 1.4a. The GTX 1660 is a dual-slot card measuring 229 mm in length, 111 mm in height, and 35 mm in width, with a 1x 8-pin power connector. The Radeon 660M is an IGP with no slot width, no power connectors, and no listed dimensions.

Specification Differences

The specification table highlights every divergence between the two parts. The Radeon 660M has a base clock of 1500 MHz and a boost clock of 1500 MHz, boosting to 1900 MHz, while the GTX 1660 has a base clock of 1530 MHz and a boost clock of 1785 MHz. The GTX 1660's memory clock is 2001 MHz with 8 Gbps effective speed.

The shading units differ by a factor of 3.7: the Radeon 660M has 384 shading units, 24 texture mapping units, and 16 render output units. The GTX 1660 has 1408 shading units, 88 TMUs, and 48 ROPs. Pixel rates follow: the Radeon 660M achieves 30.40 GPixel/s and 45.60 GTexel/s, while the GTX 1660 achieves 85.68 GPixel/s and 157.1 GTexel/s. The GTX 1660 delivers 5.027 TFLOPS of FP32 performance and 10.05 TFLOPS of FP16 (2:1), versus 1,459.2 GFLOPS and 2.918 TFLOPS for the Radeon 660M.

Thermal and power characteristics diverge as well. The Radeon 660M has a TDP of 40 W, while the GTX 1660 has a TDP of 120 W and a suggested PSU of 300 W. The GTX 1660 requires a 1x 8-pin power connector; the Radeon 660M requires none. The GTX 1660 was released on March 13, 2019, with a launch MSRP of 219 USD. The Radeon 660M was released on January 3, 2022, with no launch MSRP listed. Both are end-of-life products. The Radeon 660M's predecessor is the Vega II IGP and successor is the Navi III IGP; the GTX 1660's predecessor is GeForce 10 and successor is GeForce 20.

The Verdict

The data points in one direction only. The NVIDIA GeForce GTX 960 offers superior raw performance, but the Radeon 660M offers a lower-power integrated alternative with a smaller footprint. Users who prioritize the recorded benchmark scores should choose the GTX 1660, as it wins every head-to-head test by a margin of at least 70.6%. Users who prioritize a 40 W integrated GPU with no power connectors and system shared memory should choose the Radeon 660M, as it offers the same API support (OpenGL 4.6, Vulkan 1.4) and a ray tracing core that the GTX 1660 lacks.

Where Each One Wins

The GTX 1660 wins in every recorded benchmark category: Geekbench OpenCL and Geekbench Vulkan. Its dedicated 6 GB GDDR5 memory with 192.1 GB/s bandwidth, 1408 shading units, and 5.027 TFLOPS FP32 throughput give it a decisive edge in compute-heavy workloads. The Radeon 660M's wins are structural rather than measured: it draws only 40 W against 120 W, requires no power connector, fits as an IGP with no slot width, and uses the more advanced 6 nm process. The Radeon 660M also supports DirectX 12 Ultimate and includes 6 ray tracing cores, features absent from the GTX 1660. For users who need maximum performance per the recorded numbers, the GTX 1660 is the only choice; for users who need a low-power integrated solution with modern API features, the Radeon 660M has no direct competitor in this comparison.